Model: GPT-2 Small: 12 Layers, 3072 Neurons per Layer

Dataset: Open Web Text

Neuron 613 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('gpt2-small')

Click the toggle to see the full text!

Text #0

Max Range: 3.6098. Min Range: -3.6098

Max Act: 3.6098. Min Act: -0.1700

Data Index: 5700541 (Open Web Text)

Max Activating Token Index: 4

Text #1

Max Range: 3.6098. Min Range: -3.6098

Max Act: 3.5768. Min Act: -0.1700

Data Index: 4447138 (Open Web Text)

Max Activating Token Index: 103

Text #2

Max Range: 3.6098. Min Range: -3.6098

Max Act: 3.5062. Min Act: -0.1700

Data Index: 4798660 (Open Web Text)

Max Activating Token Index: 353

Text #3

Max Range: 3.6098. Min Range: -3.6098

Max Act: 3.4671. Min Act: -0.1700

Data Index: 7432022 (Open Web Text)

Max Activating Token Index: 3

Text #4

Max Range: 3.6098. Min Range: -3.6098

Max Act: 3.4696. Min Act: -0.1700

Data Index: 3459678 (Open Web Text)

Max Activating Token Index: 4

Text #5

Max Range: 3.6098. Min Range: -3.6098

Max Act: 3.4392. Min Act: -0.1700

Data Index: 8803108 (Open Web Text)

Max Activating Token Index: 11

Text #6

Max Range: 3.6098. Min Range: -3.6098

Max Act: 3.4000. Min Act: -0.1700

Data Index: 8093174 (Open Web Text)

Max Activating Token Index: 979

Text #7

Max Range: 3.6098. Min Range: -3.6098

Max Act: 3.3868. Min Act: -0.1700

Data Index: 6945536 (Open Web Text)

Max Activating Token Index: 27

Text #8

Max Range: 3.6098. Min Range: -3.6098

Max Act: 3.4104. Min Act: -0.1700

Data Index: 6979007 (Open Web Text)

Max Activating Token Index: 160

Text #9

Max Range: 3.6098. Min Range: -3.6098

Max Act: 3.3437. Min Act: -0.1700

Data Index: 8281714 (Open Web Text)

Max Activating Token Index: 844

Text #10

Max Range: 3.6098. Min Range: -3.6098

Max Act: 3.3547. Min Act: -0.1700

Data Index: 1063476 (Open Web Text)

Max Activating Token Index: 81

Text #11

Max Range: 3.6098. Min Range: -3.6098

Max Act: 3.3670. Min Act: -0.1700

Data Index: 2743405 (Open Web Text)

Max Activating Token Index: 1002

Text #12

Max Range: 3.6098. Min Range: -3.6098

Max Act: 3.3673. Min Act: -0.1700

Data Index: 5000746 (Open Web Text)

Max Activating Token Index: 577

Text #13

Max Range: 3.6098. Min Range: -3.6098

Max Act: 3.3590. Min Act: -0.1700

Data Index: 2612740 (Open Web Text)

Max Activating Token Index: 689

Text #14

Max Range: 3.6098. Min Range: -3.6098

Max Act: 3.3774. Min Act: -0.1700

Data Index: 896119 (Open Web Text)

Max Activating Token Index: 3

Text #15

Max Range: 3.6098. Min Range: -3.6098

Max Act: 3.3606. Min Act: -0.1700

Data Index: 6271196 (Open Web Text)

Max Activating Token Index: 483

Text #16

Max Range: 3.6098. Min Range: -3.6098

Max Act: 3.3427. Min Act: -0.1700

Data Index: 372124 (Open Web Text)

Max Activating Token Index: 756

Text #17

Max Range: 3.6098. Min Range: -3.6098

Max Act: 3.3666. Min Act: -0.1700

Data Index: 484958 (Open Web Text)

Max Activating Token Index: 150

Text #18

Max Range: 3.6098. Min Range: -3.6098

Max Act: 3.3611. Min Act: -0.1700

Data Index: 1186170 (Open Web Text)

Max Activating Token Index: 3

Text #19

Max Range: 3.6098. Min Range: -3.6098

Max Act: 3.3501. Min Act: -0.1700

Data Index: 4388635 (Open Web Text)

Max Activating Token Index: 6